Localized Schrödinger bridge sampler

DOI10.1016/J.JCP.2025.114583MaRDI QIDQ6853329zbMATH OpenFDO

Authors Georg A. Gottwald, Sebastian Reich

Publication date 25 February 2026

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2025.114583

zbMATH Keywords

Bayesian inferenceconditional independenceconditional samplingdenoisinggenerative modelingLangevin dynamicslocalizationmulti-scale closureSchrödinger bridges

Mathematics Subject Classification ID

Parametric inference (62Fxx) Probabilistic methods, stochastic differential equations (65Cxx) Artificial intelligence (68Txx)

Cites work

• A Connection Between Score Matching and Denoising Autoencoders
• A dynamical systems framework for intermittent data assimilation
• Affine-invariant ensemble transform methods for logistic regression
• Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
• Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Estimation of non-normalized statistical models by score matching
• Feedback Particle Filter
• Local MALA-within-Gibbs for Bayesian image deblurring with total variation prior
• Localization for MCMC: sampling high-dimensional posterior distributions with local structure
• MALA-within-Gibbs samplers for high-dimensional distributions with sparse conditional structure
• Markov Chains and Stochastic Stability
• Markov Random Field Modeling in Image Analysis
• Probabilistic Forecasting and Bayesian Data Assimilation
• Probabilistic graphical models.
• Solving inverse problems using data-driven models
• Spectral Convergence of Diffusion Maps: Improved Error Bounds and an Alternative Normalization
• Supervised learning from noisy observations: combining machine-learning techniques with data assimilation
• Testing the manifold hypothesis
• Tweedie’s Formula and Selection Bias
• What regularized auto-encoders learn from the data-generating distribution

Cited in

(1)

• Digital twins: McKean-Pontryagin control for partially observed physical twins

This page was built for publication: Localized Schrödinger bridge sampler

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6853329)